According to ChainCatcher citing The Verge, OpenAI is gradually rolling out GIF generation in ChatGPT, powered by its unannounced Images 2.6 model. Users can describe an animation in natural language or upload a photo to turn into a GIF, then adjust playback speed, view frames, edit, and share the result.
The Images 2.6 update also promises faster image generation and is being rolled out to ChatGPT and Codex users on web, desktop, and mobile. Developers will get two API models, GPT-Image-2.6 Flare for faster generation and GPT-Image-2.6 Sunburst for higher-quality results. OpenAI has not published a standalone announcement detailing the model’s capabilities or said when GIF generation will reach all ChatGPT accounts; most users cannot access it yet.
The update follows the September release of ChatGPT Images 2.5, which brought sharper detail, more precise editing, and generation speeds up to 50% faster than its predecessor. OpenAI shut down its standalone AI video-generation app Sora in March.